International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
Volume 186 - Issue 56 |
Published: December 2024 |
Authors: Neji Kouka, Jawaher Ben Khalfa, Jalel Eddine Hajlaoui |
![]() |
Neji Kouka, Jawaher Ben Khalfa, Jalel Eddine Hajlaoui . Going More Deeper With Convolutions for Network in Network. International Journal of Computer Applications. 186, 56 (December 2024), 35-38. DOI=10.5120/ijca2024924286
@article{ 10.5120/ijca2024924286, author = { Neji Kouka,Jawaher Ben Khalfa,Jalel Eddine Hajlaoui }, title = { Going More Deeper With Convolutions for Network in Network }, journal = { International Journal of Computer Applications }, year = { 2024 }, volume = { 186 }, number = { 56 }, pages = { 35-38 }, doi = { 10.5120/ijca2024924286 }, publisher = { Foundation of Computer Science (FCS), NY, USA } }
%0 Journal Article %D 2024 %A Neji Kouka %A Jawaher Ben Khalfa %A Jalel Eddine Hajlaoui %T Going More Deeper With Convolutions for Network in Network%T %J International Journal of Computer Applications %V 186 %N 56 %P 35-38 %R 10.5120/ijca2024924286 %I Foundation of Computer Science (FCS), NY, USA
Network in Network is an important extension of the deep convolution neural network that uses a shallow multilayer perceptron (MLP), a nonlinear function, to replace the linear filter. In this article, we propose to replace convolution layers with convolution modules. The main feature of this architecture is the improved utilization of computing resources inside the network. This has been achieved through a carefully crafted design that allows for increased network depth and width while keeping the compute budget constant. The experimental results on the CIFAR10 dataset demonstrate the effectiveness of the proposed method.